The first BlockDAG built for decentralized AI inference. Proof-of-Model. Unstoppable intelligence.
Three corporations control the filters of global AI. On-chain agents can't run local models. They need a decentralized inference layer.
AI providers quietly modify model outputs to align with corporate policies. No transparency, no audit trail, no recourse.
Every query passes through centralized servers. Your questions, strategies, and private data — logged, analyzed, monetized.
The model runs across thousands of sovereign miners. No kill switch. Intelligence becomes a public infrastructure.
Miners lock 20% of every block as a bond. Advertise a model and fail to serve it, and the bond burns — three strikes suspends you for 24h.
Keryx's proof-of-work isn't arbitrary hashing — it's the model itself. To win a block, a miner's GPU must actually hold a full AI model in memory.
Mining requires a model's weights resident in VRAM. No idle hashing on a bare GPU — the work is the model.
The proof-of-work walks the resident weights — each read's location derived from the last. A partial copy can't precompute or stream fast enough: miss a fraction of the weights and you slow down by orders of magnitude.
The largest model your VRAM holds sets your tier — from Qwen3.5-9B on an 8 GB card to Kimi-Linear-48B on a 32 GB card. Heavier tier, larger block reward.
Verification is byte-exact and fully deterministic: a per-tier weight Merkle root plus Fiat-Shamir chunk openings, checked from the block header alone. Pool-safe and fork-proof — no trust in the miner.
PoM proves a miner holds the model, byte-exactly, at the consensus level — and the service bond proves they answer. Both are re-derived from the block by every node, with no attestation service and no committee in the path. The network's capacity is a floor you can read off the chain, not a figure its operators assert.
Prove you hold the weights. Answer when assigned. Both are checked by every node.
User or AI agent submits an AI_Request to the mempool with model ID and fees.
An eligible miner — one that has proven the requested tier within the last ~5 minutes — runs the model and publishes the response.
The miner's 20% bond stays timelocked for 792,000 blocks (~22h). Miss an assignment and escrow claims burn; a third strike suspends the payout for 24h.
The result CID is on-chain and immutable. The request escrow releases to the miner who served it; the bond returns when its timelock expires.
Strikes and suspensions follow the payout address, not the hot escrow key — so a miner can rotate keys on a rig freely, but cannot shed a record by starting a fresh address. A new identity spends 504,000 blocks (~14h) on probation, earning the floor tier rate of 60% whatever tier its hardware proves. Walking away from a strike costs up to 40% of the miner cut for fourteen hours; absorbing it costs less. The unpaid remainder is burned, so nobody profits from anyone else's probation.
A fully uncensored lineup — no corporate filters, no refusals. Every model is identified by sha2-256(weight_file) — the hash extracted directly from its IPFS CID. A miner cannot fake which model it runs. Requesters set a priority_fee above the minimum to be served first.
Light and unfiltered. Runs on an 8 GB GPU — the entry tier for high-frequency agent calls and synthetic workloads.
Balanced reasoning and speed, no corporate filters. Suitable for complex queries, on-chain agent decisions, and multi-step logic.
Unfiltered mid-tier for 16 GB cards. Strong general reasoning and instruction-following, sitting between the 9B tier and Qwen3.6-27B.
High-fidelity reasoning at scale, unrestricted. A hybrid SSM/attention architecture for deep analysis, code generation, and long-context understanding.
State-of-the-art open MoE, fully unfiltered — 48B total, 3B active per token. The Q4_K_M quant fits a single 32 GB card. Reserved for the most demanding autonomous agent workflows.
Requesters can bid above the minimum to jump the queue. Miners serve the highest-paying requests first — creating a real market for inference priority. Every fee is paid in $KRX, creating direct, measurable buy pressure from actual AI usage.
Whether for humans seeking truth without filters or autonomous agents operating on-chain, Keryx is the trustless backbone of decentralized intelligence.
Solana and Ethereum AI agents are, today, fully centralized via Web2 APIs. Smart contracts are deterministic — they cannot reason, interpret language, or make decisions, so the moment an agent has to think it calls OpenAI or Anthropic and inherits their kill switch. With Keryx, an agent broadcasts an AiRequest on-chain, a miner executes the inference, and the result comes back as an on-chain AiResponse — no HTTP call, no API key, no corporate gateway. The serving miner has proven on-chain that they hold the model they answered with, and forfeits collateral if they refuse to answer. The chain is the oracle.
Legal, medical, or political queries without corporate filters. A neutral AI that answers factually regardless of the topic.
Roadmap: users encrypt their prompt with the miner's public key before broadcasting. The miner decrypts and runs inference locally — the plaintext prompt never appears on-chain in any form. The on-chain CID still commits to the exact bytes returned, so the answer cannot be altered after the fact, while keeping the query private.
Designed for long-term scarcity. Every transaction destroys value. Every block splits reward between miners, infrastructure, and protocol burn.